vanchin/deepseek-v4-pro

Updated at:

DeepSeek-V4(MoE), includes DeepSeek-V4-Pro(1.6T, 49B).100(1M)token, 32Ttoken.

Inference Service Provider

The inference service provider for vanchin/deepseek-v4-pro is Kuaishou Vanchin.

Model Capabilities

CapabilitySupportCapabilitySupport

Input Modality

Text

Output Modality

Text

Model Experience

Unsupported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Unsupported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

ParameterValueParameterValue

Max Input Length

1048576

Max Output Length

393216

Context Window

1048576

Max Input Length (Thinking Mode)

1048576

Max Output Length (Thinking Mode)

393216

Pricing

This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.

China (Beijing)

Billing ItemPrice (CNY)Unit

Input

12

Per 1M tokens

Output

24

Per 1M tokens

Input(Implicit Cache)

1

Per 1M tokens

Rate Limits

China (Beijing)

ParameterValue

RPM (Requests Per Minute)

60

TPM (Tokens Per Minute)

300,000